基于在线聚类算法的发动机空燃比自适应模糊模型

为了描述煤层气发动机强烈的非线性和解决动态工况下空燃比控制的延迟问题,采用在线聚类算法建立了排气空燃比自适应模糊模型。通过在线聚类算法更新T-S模糊模型结构,基于递推加权最小二乘（WRLS）算法辨识结论参数,结合加权平均算法预测空燃比。动态工况下的实验验证表明,空燃比自适应模糊模型能够补偿延迟,精确捕获空燃比的瞬态偏移。     

蚁群初始化小波网络的汽油机油膜参数辨识研究

建立瞬态工况小波网络发动机油膜模型,利用蚁群算法对小波网络参数进行初始化寻优,将其作为小波网络参数初始值,以提高小波网络的训练速度和误差精度,并基于该网络模型测试了发动机空燃比瞬态过程,然后利用瞬态工况试验数据进行了仿真,并与台架试验实际数据进行对比。结果表明,基于蚁群算法初始化小波网络模型能有效地辨识发动机瞬态工况油膜参数,高精度地逼近空燃比瞬态过程,不仅具有较强的泛化能力,而且大大缩短了训练时间。蚁群初始化小波网络适用于油膜参数辨识,本研究为发动机瞬态工况空燃比的精确控制奠定了基础。     

汽油机三效催化转换器故障诊断模型的研究

深入研究了汽油机三效催化转换器氧存贮故障诊断模型,该模型结构简单,适合数据实时处理,模型参数的精确估计是保证模型精度的关键.基于发动机空燃比"浓稀"法控制,监测尾气通过催化器后空燃比变化,间接估计催化器内氧存贮状态,结合加权递推最小二乘算法估计模型参数,并进行了Simulink仿真.仿真结果表明参数估计方法有效,催化器氧存贮模型具有较高的精度.     

基于神经网络的预测算法在CNG发动机空燃比控制中的应用研究

针对天然气发动机本身的非线性特点和空燃比传输延迟的特性,提出了一种基于神经网络预测的空燃比控制策略,利用Matlab/Simulink建立控制器的算法模型,以dSPACE公司的MicoAutoBox为算法实施平台,在NQ150N型天然气发动机上进行了实验测试,实验结果表明,与普通PID控制算法相比,基于神经网络预测的控制算法稳态性能优良,能明显改善过度工况空燃比的控制效果.     

瞬态空燃比控制策略研究及智能控制的应用

介绍了基于平均值模型的汽油发动机瞬记空燃比控制策略，及人工智能和神经网络技术在模型参数辨识中的应用。     

基于改进鸡群优化算法的质子交换膜燃料电池模型参数辨识

针对当前大部分智能算法在求解质子交换膜燃料电池模型参数辨识问题时易陷入局部最优,导致参数辨识精度低、模型泛化能力差等问题,提出一种基于改进鸡群优化算法的质子交换膜燃料电池模型参数辨识方法。首先,引入Tent映射策略初始化种群,提高种群的均匀性和遍历性;其次,设计基于个体进食速度的自适应惯性权重,改善母鸡个体寻优效率,平衡算法的开发与探索能力;然后,利用Levy飞行策略的长短跳跃特点对小鸡位置进行随机更新,增强算法的全局最优搜索能力。最后,通过4组测试函数验证了该算法的优越性,并将算法应用于H-12电堆的参数辨识问题中。结果表明：相比于鲸鱼优化算法、花卉授粉算法等算法,该算法具有更高的参数辨识精度,所辨识出的模型具有更强的泛化能力。     

基于模型在环仿真的直喷汽油机空燃比辨识与控制研究

针对过渡工况下汽油机空燃比难以精确控制的特点,将PID神经元网络(proportional-integral-derivative neural network,PIDNN)控制策略用于发动机常用的部分负荷工况下空燃比的辨识与控制。在AMESim中,从实际发动机物理模型出发建立了发动机仿真模型;同时在Matlab软件中建立PIDNN辨识器、PIDNN控制器;通过Matlab和AMESim软件的耦合进行模型在环仿真,建立电喷发动机实时控制系统,通过联合仿真观察辨识效果,同时检验控制系统的性能。模型在环仿真结果表明:PIDNN辨识器能够快速跟踪实际空燃比的变化,辨识系统的输出与发动机模型的输出误差在0.05之内;在过渡工况下,PIDNN控制器控制下的过量空气系数超调量相对于普通PID控制器能减小0.3以上,同时能在2s内将过量空气系数控制至目标值,提高了空燃比的控制精度。     

基于线性神经网络的煤层气发动机空燃比动态建模

针对预混合双阀控制的煤层气发动机,利用引入动态环节的递归线性神经网络,基于台架实验所获得的数据建立煤层气发动机空燃比动态过程的输入/输出模型.以均方差为评价指标确定模型输入、输出的阶次,用非建模数据对训练后的模型进行验证.结果表明,模型准确复现了不同工况下空气和燃气质量流量与排气空燃比的动态特性.     

基于模型的怠速空燃比PID控制策略的研究

本文借助于车载动态实验数据,采用系统辨识的方法建立喷气脉宽与空燃比之间的动态模型.在此基础上应用位置式和增量式两种PID控制策略进行反馈控制.仿真结果表明,尽管位置式PID反馈控制输出很快收敛到设定理论空燃比,并维持在理论空燃比,但考虑到其每次输出均与过去的状态有关,并对空燃比偏差进行累加,在实际使用时有可能引发重大事故;而离散增量式PID控制算法不但对控制目标的调节时间短,而且对扰动具有更好的鲁棒性,控制精度较高.     

天然气发动机怠速控制策略的研究

为了提高自然吸气式多点喷射单燃料压缩天然气(CNG)发动机怠速工况时转速和空燃比综合控制的稳态和动态效果,设计了一种怠速模糊控制策略,介绍了控制算法的设计过程.利用Matlab/Simulink建立了整个怠速系统仿真模型,并进行控制算法的开发和测试,仿真结果证明,该仿真模型能够正确反映出发动机转速和空燃比的各种变化过程,控制算法具有较好的控制效果.最后发动机台架试验表明,该控制策略使怠速稳态、脱离和进入怠速的瞬态工况下的转速和空燃比都得到了精确的控制,提高了怠速品质,对发动机参数的变化具有一定的鲁棒性.     

Automotive fuel cell engine test cell design and its thermal flow analysis

A test cell for automotive PEM fuel cell engine is introduced and designed. Similarities and differences of facilities between PEM fuel cell engine and inner-combustion engine are illustrated. It turns out that, the air treatment, exhaust gas, cooling and electrical facilities are quite similar, the fuel treatment, power load type, ventilation and air-conditioning are quite different, while the vibration isolation and noise elimination facilities are completely simplified. Furthermore, a thermodynamic model is proposed to analysis the heat flow in fuel cell engine test cell. The Monte Carlo Simulation method is applied to get the proportion of outgoing thermal flows. A thermal flow rule of 4.5/4.5/0.6/0.4 is proposed as rule of thumb for cell designer.     

Low power proton exchange membrane fuel cell system identification and adaptive control

This paper proposes a systematic method of system identification and control of a proton exchange membrane (PEM) fuel cell. This fuel cell can be used for low-power communication devices involving complex electrochemical reactions of nonlinear and time-varying dynamic properties. From a system point of view, the dynamic model of PEM fuel cell is reduced to a configuration of two inputs, hydrogen and air flow rates, and two outputs, cell voltage and current. The corresponding transfer functions describe linearized subsystem dynamics with finite orders and time-varying parameters, which are expressed as discrete-time auto-regression moving-average with auxiliary input models for system identification by the recursive least square algorithm. In the experiments, a pseudo-random binary sequence of hydrogen or air flow rate is fed to a single fuel cell device to excite its dynamics. By measuring the corresponding output signals, each subsystem transfer function of reduced order is identified, while the unmodeled, higher-order dynamics and disturbances are described by the auxiliary input term. This provides a basis of adaptive control strategy to improve the fuel cell performance in terms of efficiency, as well as transient and steady state specifications. Simulation shows that adaptive controller is robust to the variation of fuel cell system dynamics, and it has proved promising from the experimental results.     

A new parameter extraction method for accurate modeling of PEM fuel cells

In this paper, a new parameter extraction method for accurate modeling of proton exchange membrane (PEM) fuel cell systems is presented. The main difficulty in obtaining an accurate PEM fuel cell dynamical model is the lack of manufacturer information about the exact values of the parameters needed for the model. In order to obtain a realistic dynamic model of the PEM system, the electrochemical considerations of the system are incorporated into the model. Although many models have been reported in the literature, the parameter extraction issue has been neglected. However, model parameters must be precisely identified in order to obtain accurate simulation results. The main contribution of the present work is the application of the simulated annealing (SA) optimization algorithm as a method for identification of PEM fuel cell model parameter identification. The major advantage of SA is its ability to avoid becoming trapped in local minimum, as well as its flexibility and robustness. The parameter extraction and performance validation are carried out by comparing experimental and simulated results. The good agreement observed confirms the usefulness of the proposed extraction approach together with adopted PEM fuel cell model as an efficient tool to help design of power fuel cell power systems. Copyright © 2009 John Wiley & Sons, Ltd.     

Design and experimental implementation of time delay control for air supply in a polymer electrolyte membrane fuel cell system

This paper studies the air flow control for preventing the starvation and/or obtaining the maximum net power of a Polymer Electrolyte Membrane (PEM) fuel cell system using time delay control (TDC). Feedforward and feedback controls are utilized simultaneously to prevent air shortage during the transient response of the fuel cell operation. The TDC algorithm design is created with a low-order dynamic model, and its superior performances are proven using a real-time control experiment. The optimal air excess ratio is calculated experimentally given the variation of the external load, and the net power increase is discussed by comparison with the results obtained from fixed air excess ratio. The Ballard 1.2 kW PEM fuel cell system is used for the experiments as a test rig, and the LabView system is used for the real-time air flow control. The superiority of the TDC performance is proven by comparison with other control algorithms such as the proportional–integral control (PIC), feedforward control, and the original manufacturer's control. The proposed control algorithm can improve PEM fuel cell system performance by preventing air shortage and/or by obtaining higher performance.     

Fuel consumption and emission comparison of conventional and hydrogen feed vehicles

Current environmental concerns on nitrogen oxides (NO_x) and particulate matter (PM) emissions caused by diesel engines have led researchers to be interested in investigating vehicles with alternative power sources. Because of this reason, vehicle models with SI engine were adopted in the conducted study. Firstly, as an initial step, 1-D SI engine models were created with use of AVL Boost software. A four-cylinder engine model was created for conventional vehicle model, while a two-cylinder downsized engine was adopted as a subsystem of hybrid vehicle model. The models were based on experimental data obtained from a laboratory test setup with a single-cylinder engine. Subsequently, detailed engine maps on emissions and fuel consumption were generated with the developed ANN model. The fuel consumption and emission data, which were gathered from NEDC and WLTC simulations, were compared for conventional ICE, PEM FC and PEM FC + ICE powered vehicles with the help of the vehicle model which was developed by using Matlab Simulink software. Based on the results, it was concluded that there might be sufficient improvement in fuel consumption and significant improvement in emissions with the use of PEM FC that a hybrid driving system (PEM FC + ICE) can be utilized, and that emissions can be at 0 with the sole use of PEM FC.     

氧传感器参考电平自适应空燃比闭环控制方法研究

为了解决开关式氧传感器空燃比闭环控制点的漂移问题，建立了开关式氧传感器闭环控制的数学模型，并分析了氧传感器信号参考电平对空燃比闭环控制的影响，据此，提出了氧传感器参考电平自适应空燃比闭环控制方法，在发动机上试验了氧传感器参考电平对空燃比的影响规律，并进行了氧传感器参考电平的优化试验，结果表明，氧传感器参考电平自适应控制方法可以有效避免空燃比闭控制点随发动机工况变化的漂移问题，有效地降低了汽油机的排放。     

基于RBF神经网络的电喷天然气发动机空燃比控制

电喷天然气发动机空燃比在工况突变时会剧烈波动,为提高控制精度,使用RBF神经网络和前馈PID控制算法相结合,由当前工况决定燃料基本喷射量,再由RBF神经网络预测的空燃比信号传递给PID控制器进行反馈调节。此外利用Matlab/Simulink软件进行仿真,建立了电喷天然气发动机空燃比仿真模型。仿真结果表明,该控制方法在节气门及发动机转速突变的情况下,过渡时间较PID算法明显减小,控制精度亦有提高。     

Time delay control for fuel cells with bidirectional DC/DC converter and battery

Transient behavior is a key property in the vehicular application of proton exchange membrane (PEM) fuel cells. A better control technology is constructed to increase the transient performance of PEM fuel cells. A steady-state isothermal analytical fuel cell model is constructed to analyze mass transfer and water transport in the membrane. To prevent the starvation of air in the PEM fuel cell, time delay control is used to regulate the optimum stoichiometric amount of oxygen, although dynamic fluctuations exist in the PEM fuel cell power. A bidirectional DC/DC converter connects the battery to the DC link to manage the power distribution between the fuel cell and the battery. Dynamic evolution control (DEC) allows for adequate pulse-width modulation (PWM) control of the bidirectional DC/DC converter with fast response. Matlab/Simulink/Simpower simulation is performed to validate the proposed methodology, increase the transient performance of the PEM fuel cell system and satisfy the requirement of energy management.     

Improving dynamic performance of proton-exchange membrane fuel cell system using time delay control

Transient behaviour is a key parameter for the vehicular application of proton-exchange membrane (PEM) fuel cell. The goal of this presentation is to construct better control technology to increase the dynamic performance of a PEM fuel cell. The PEM fuel cell model comprises a compressor, an injection pump, a humidifier, a cooler, inlet and outlet manifolds, and a membrane-electrode assembly. The model includes the dynamic states of current, voltage, relative humidity, stoichiometry of air and hydrogen, cathode and anode pressures, cathode and anode mass flow rates, and power. Anode recirculation is also included with the injection pump, as well as anode purging, for preventing anode flooding. A steady-state, isothermal analytical fuel cell model is constructed to analyze the mass transfer and water transportation in the membrane. In order to prevent the starvation of air and flooding in a PEM fuel cell, time delay control is suggested to regulate the optimum stoichiometry of oxygen and hydrogen, even when there are dynamical fluctuations of the required PEM fuel cell power. To prove the dynamical performance improvement of the present method, feed-forward control and Linear Quadratic Gaussian (LQG) control with a state estimator are compared. Matlab/Simulink simulation is performed to validate the proposed methodology to increase the dynamic performance of a PEM fuel cell system.     

单点燃油喷射式火花点火发动机进气系统的建模

讨论单点燃油喷射式火花点火发动机的非线性动态模型，该模型可用于控制算法的火花点火式发动机开发研究。针对空燃比控制，模型建立从节气门和进气歧管两方面进行，所建模型可采用控制算法对其进行实时控制和系统仿真，模型的复杂程度足以代表一般的火花点火式发动机，模型中的参数可以通过实机测试或仿真来设置。